Training in progress, step 42000, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16df4d6de6762c1f1db0594493c5dbe4807fbb7aeb4ffb34555825a9d9d04146
+oid sha256:ce663d57bd5e6360f5aa5cde979cae8f2a9beb87ec8ad5d9e19aab2702fbed10
 size 4978139416

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab626964d3a443836bb0b91fb446a151856aea70c73efd8f48b4c8d2ea0d0396
+oid sha256:63b4fc9e148d4095e7c5e2b8e632fc2cc799420a45ba0a97083a74234c7e4a0b
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53e26564465c0e121b7bea0b1e6e7ce1fd43de5ee568c559280ebef58a187e5d
+oid sha256:a2aea64ca95212592eed9b56eb02336a03d719884900412b4b4989614fcafaea
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68121decba33fc890b293e4256e209b83c963a48989e0b33e6ef62cd27e6b943
+oid sha256:52359c232c36eef781bea5a792c80ae0230d6dd8b695036813025c3aec557007
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c93fb241eedaa94832e6d27b22d2591980d2a3312c84d793dfe2f6489464b54
+oid sha256:d70e777ba7501545daa9cec71c8f0943a8410c0ddb684a9fa8fb46c49eb4d9a0
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.59629551673332,
+  "epoch": 17.68048831824879,
   "eval_steps": 100,
-  "global_step": 41800,
+  "global_step": 42000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6695,6 +6695,38 @@
       "eval_samples_per_second": 24.761,
       "eval_steps_per_second": 3.096,
       "step": 41800
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 2.0896823406219482,
+      "learning_rate": 2.075547703180212e-05,
+      "loss": 0.6531,
+      "step": 41900
+    },
+    {
+      "epoch": 17.64,
+      "eval_cer": 0.3638618943334246,
+      "eval_loss": 1.911123514175415,
+      "eval_runtime": 401.57,
+      "eval_samples_per_second": 23.602,
+      "eval_steps_per_second": 2.951,
+      "step": 41900
+    },
+    {
+      "epoch": 17.68,
+      "grad_norm": 2.2857401371002197,
+      "learning_rate": 2.068480565371025e-05,
+      "loss": 0.6536,
+      "step": 42000
+    },
+    {
+      "epoch": 17.68,
+      "eval_cer": 0.3620947557780298,
+      "eval_loss": 1.524117112159729,
+      "eval_runtime": 379.6794,
+      "eval_samples_per_second": 24.963,
+      "eval_steps_per_second": 3.121,
+      "step": 42000
     }
   ],
   "logging_steps": 100,
@@ -6702,7 +6734,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.5813049896121755e+20,
+  "total_flos": 4.602974079911708e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null